SKILLEMALL.ai
GitHub ↗ RU Sign in

CD it-consulting-workbench

【IT咨询顾问 / AI咨询顾问 / 数字化转型顾问 / CIO顾问 超级工作台 / IT Consulting & AI Transformation Advisor Workbench】 ——面向IT战略规划、企业AI转型、技术尽调、供应商选型、企业架构设计、数字化成熟度评估、IT治理、 IT财务管理、网络安全评估、云迁移规划、数据战略与治理、数据中台、业务中台、主数据管理(MDM)、 敏捷转型、DevOps转型、低代码平台选型、IT外包管理、IT审计、变革管理、IT组织设计、 项目实施管控、高管汇报等全场景IT咨询的全栈自动化技能。 ■ 角色覆盖：无论你被称为 IT咨询顾问、IT顾问、AI咨询顾问、AI转型顾问、数字化转型顾问、数字化顾问、 CIO顾问、IT战略顾问、企业架构师、EA、技术咨询顾问、技术顾问、IT规划师、信息化规划师、管理咨询顾问、 科技咨询顾问、解决方案架构师、售前顾问、IT项目经理、PMO —— 这个 Skill 都能胜任你的核心工作。 ■ 方法论驱动：内置 MECE 结构化分解、假设驱动 (Hypothesis-Driven)、金字塔原理 (Pyramid Principle)、 SCQA 叙事框架、Issue Tree / Driver Tree、5-Why 根因分析、80/20 帕累托法则、ADKAR 变革模型、 Kotter 8步变革法、TOGAF ADM 企业架构、NIST CSF 2.0 安全框架、6R 云迁移框架、 AIM² AI成熟度模型 (L1-L5)、RICE+ AI用例评分、Five Case Model 商业论证、FinOps 三阶段、 DORA DevOps 指标、ITIL 4 服务管理、Well-Architected Framework。 ■ 全生命周期覆盖 (8阶段57文件)： 阶段0-商机开发与签约：初次客户沟通 → 需求澄清与问题诊断(MECE五维) → 项目建议书Proposal(9章) → SOW合同与谈判 阶段1-项目启动与诊断：项目章程与团队组建 → 利益相关者访谈(四波法) → IT现状五维诊断(技术/流程/组织/数据/财务) → 诊断报告撰写(发现→洞察→建议) 阶段2-战略与方案设计：IT战略规划(SoR/SoD/SoI+Run/Grow/Transform) → AI转型战略(AIM²+RICE+) → 企业架构设计(TOGAF四层) → 云战略与迁移规划(6R+FinOps) → 数据战略与治理(Data Mesh/Lakehouse) → 安全战略与风险管理(NIST CSF 2.0+零信任) 阶段3-技术评估与选型：技术尽调(架构/代码/安全/团队四维) → RFP全流程(8-12周) → 供应商评估与选型(评分→演示→PoC→参考调查) 阶段4-财务分析与商业论证：TCO总拥有成本分析(5年+隐性成本) → ROI与商业论证(NPV/IRR/Payback) → FinOps与成本优化(三阶段) 阶段5-变革管理与组织设计：变革管理(ADKAR+Kotter+采用度仪表盘) → IT组织设计(平台+产品模式) 阶段6-实施落地与PMO：项目实施管理(三层治理+质量门+变更管理) → 供应商管理(记分卡+QBR+SLA) 阶段7-交付与收尾：高管汇报(SCQA+金字塔原理+30秒结论) → 项目验收与收尾 → 知识转移与后续合作 ■ 内置12个填空式交付物模板：Proposal项目建议书、诊断报告、IT战略规划报告、AI转型路线图、 商业论证Business Case、RFP需求建议书、供应商评分卡、TCO分析、变革管理计划、董事会汇报PPT结构、 SteerCo月度评审、项目验收报告。每个模板填公司名即可用。 ■ 对标6家顶尖咨询公司：McKinsey(结构化思维) + Bain(结果导向) + BCG(战略高度) + Accenture(工程全栈交付) + Deloitte(行业深度) + Thoughtworks(敏捷现代化)。 ■ 触发词覆盖90+中英文别名：IT咨询、IT咨询顾问、AI咨询、AI咨询顾问、数字化转型、数字化转型顾问、 数字化成熟度评估、数字化成熟度、CIO顾问、IT战略、IT战略规划、信息化规划、信息系统规划、 数字化规划、IT规划、IT治理、IT财务管理、企业架构、企业架构设计、EA、TOGAF、技术架构、 技术咨询、技术顾问、管理咨询、战略咨询、科技咨询、AI转型、人工智能转型、技术尽调、科技尽调、 IT尽调、供应商选型、供应商评估、RFP、需求建议书、招标、ERP选型、CRM选型、SaaS选型、 低代码平台选型、低代码、TCO、总拥有成本、ROI、投资回报、商业论证、Business Case、 FinOps、I

ClawHub Agent Skills author: yinjianheng v1.2.0 MIT-0 59 files body ≈ 6 017 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

【IT咨询顾问 / AI咨询顾问 / 数字化转型顾问 / CIO顾问 超级工作台 / IT Consulting & AI Transformation Advisor Workbench】 ——面向IT战略规划、企业AI转型、技术尽调、供应商选型、企业架构设计、数字化成熟度评估、IT治理、…

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerProcurementtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
74/100
safety, quality, tests
Safety 60%
100
Quality 40%
34
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. Shorten the description to 1024 characters.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 59. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 2729 chars, limit 1024
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 6017 tokens (recommended < 5000); move details to references/
  • note description-budget description takes 2729 of the ~15000-char shared budget for all skills
  • note frontmatter-key unknown frontmatter key "language"
  • note frontmatter-key unknown frontmatter key "contact"

Process rating: all ten parameters 49/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 70Execution cost. Instruction body is 6017 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 41 steps
  • 100Consistency. Name and required fields are in place
  • low 26 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 2729: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +4Structure: 68 headings
  • +3Step-by-step instructions: 41 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 34.

External checks

ClawHub: clean
This is a markdown-only IT consulting playbook with some broad and privacy-sensitive guidance, but no hidden execution, exfiltration, persistence, or deceptive install behavior.
LLM: benign (medium) · VirusTotal: · 10 Jul 2026